Chrisyichuan commited on
Commit
6af1bca
·
1 Parent(s): a2d3b74
Files changed (1) hide show
  1. README.md +167 -58
README.md CHANGED
@@ -10,21 +10,54 @@ app_file: app.py
10
  pinned: false
11
  ---
12
 
13
- # Omniscient
14
- "The all-knowing AI that sees everything, knows everything"
15
 
16
- A versatile AI bot for image analysis and dataset curation with support for multiple AI models.
 
17
 
18
- ## Features
 
 
 
19
 
20
- - **Dataset Curation**: Generate and curate image datasets
21
- - **Single Image Analysis**: Benchmark different AI models on individual images
22
- - **Agentic Analysis**: Multi-step AI reasoning and analysis
23
- - **Multiple AI Providers**: Support for OpenAI, Anthropic, and Google AI
24
 
25
- ## Quick Start
26
 
27
- ### 1. Setup Environment
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
 
29
  ```bash
30
  cd simple_G_ai_bot
@@ -33,112 +66,188 @@ cd simple_G_ai_bot
33
  Create a `.env` file in the project root:
34
 
35
  ```bash
36
- # .env
37
  OPENAI_API_KEY=your_openai_api_key_here
38
  ANTHROPIC_API_KEY=your_anthropic_api_key_here
39
  GOOGLE_API_KEY=your_google_api_key_here
40
  ```
41
 
42
- ### 2. Install Dependencies
43
 
44
  ```bash
45
  uv sync
46
  ```
47
 
48
- ### 3. Usage Examples
 
 
 
49
 
50
- #### Dataset Curation
51
  Generate 50 urban outdoor samples:
52
  ```bash
53
  python main.py --mode data --samples 50 --urban --no-indoor
54
  ```
55
 
56
- #### Single Image Analysis
 
 
 
 
57
  Benchmark GPT-4o on 5 samples:
58
  ```bash
59
  python main.py --mode benchmark --models gpt-4o --samples 5
60
  ```
61
 
62
- #### Agentic Analysis
 
 
 
 
63
  Run multi-step analysis with Gemini:
64
  ```bash
65
  python main.py --mode agent --model gemini-2.5-pro --steps 10 --samples 5
66
  ```
67
 
68
- ## Configuration
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
- ### Environment Variables
71
 
72
- | Variable | Description | Required |
73
- |----------|-------------|----------|
74
- | `OPENAI_API_KEY` | OpenAI API key for GPT models | Optional |
75
- | `ANTHROPIC_API_KEY` | Anthropic API key for Claude models | Optional |
76
- | `GOOGLE_API_KEY` | Google AI API key for Gemini models | Optional |
77
 
78
- ### Command Line Options
79
 
80
- #### Common Options
81
- - `--mode`: Operation mode (`data`, `benchmark`, `agent`)
82
- - `--samples`: Number of samples to process (default: 10)
 
83
 
84
- #### Data Mode Options
85
- - `--urban`: Focus on urban environments
86
- - `--no-indoor`: Exclude indoor scenes
87
 
88
- #### Benchmark Mode Options
89
- - `--models`: AI model to use (e.g., `gpt-4o`, `claude-3`, `gemini-pro`)
90
 
91
- #### Agent Mode Options
92
- - `--model`: AI model for agentic analysis
93
- - `--steps`: Number of reasoning steps (default: 5)
94
 
95
- ## Supported Models
 
 
 
96
 
97
- - **OpenAI**: GPT-4o, GPT-4, GPT-3.5-turbo
98
- - **Anthropic**: Claude-3-opus, Claude-3-sonnet, Claude-3-haiku
99
- - **Google**: Gemini-2.5-pro, Gemini-pro, Gemini-pro-vision
 
 
 
 
 
 
 
 
 
 
100
 
101
- ## Requirements
 
 
 
102
 
103
- - Python 3.8+
104
- - UV package manager
105
- - Valid API keys for desired AI providers
106
 
107
- ## Installation
108
 
109
- 1. Clone the repository
110
- 2. Navigate to project directory: `cd simple_G_ai_bot`
111
- 3. Create `.env` file with your API keys
112
- 4. Install dependencies: `uv sync`
113
- 5. Run the bot with desired mode and options
114
 
115
- ## Examples
116
 
117
- ### Basic Dataset Generation
118
  ```bash
119
  python main.py --mode data --samples 20
120
  ```
121
 
122
- ### Urban Scene Analysis
123
  ```bash
124
  python main.py --mode data --samples 30 --urban --no-indoor
125
  ```
126
 
127
- ### Model Comparison
128
  ```bash
 
129
  python main.py --mode benchmark --models gpt-4o --samples 10
 
 
130
  python main.py --mode benchmark --models claude-3-opus --samples 10
131
  ```
132
 
133
- ### Advanced Agentic Workflow
134
  ```bash
135
  python main.py --mode agent --model gemini-2.5-pro --steps 15 --samples 3
136
  ```
137
 
138
- ## Security Note
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
 
140
- ⚠️ **Important**: Never commit your `.env` file to version control. Add `.env` to your `.gitignore` file to keep your API keys secure.
 
 
141
 
142
- ## License
143
 
144
- MIT License - see LICENSE file for details.
 
10
  pinned: false
11
  ---
12
 
13
+ <div align="center">
 
14
 
15
+ # 🧠 Omniscient
16
+ ### *"The all-knowing AI that sees everything, knows everything"*
17
 
18
+ [![Python](https://img.shields.io/badge/Python-3.8+-blue.svg)](https://python.org)
19
+ [![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
20
+ [![Streamlit](https://img.shields.io/badge/Streamlit-1.35.0-red.svg)](https://streamlit.io)
21
+ [![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-Space-yellow.svg)](https://huggingface.co/spaces/Omniscient001/Omniscient)
22
 
23
+ *A versatile AI bot for image analysis and dataset curation with support for multiple AI models*
 
 
 
24
 
25
+ 🎮 **[Try it Live on HuggingFace!](https://huggingface.co/spaces/Omniscient001/Omniscient)** *(Actively WIP)*
26
 
27
+ </div>
28
+
29
+ ---
30
+
31
+ ## ✨ Features
32
+
33
+ <table>
34
+ <tr>
35
+ <td width="50%">
36
+
37
+ ### 🗃️ **Dataset Curation**
38
+ Generate and curate high-quality image datasets with intelligent filtering and categorization.
39
+
40
+ ### 🔍 **Single Image Analysis**
41
+ Benchmark different AI models on individual images with detailed performance metrics.
42
+
43
+ </td>
44
+ <td width="50%">
45
+
46
+ ### 🤖 **Agentic Analysis**
47
+ Multi-step AI reasoning and analysis with advanced decision-making capabilities.
48
+
49
+ ### 🌐 **Multiple AI Providers**
50
+ Seamless integration with OpenAI, Anthropic, and Google AI platforms.
51
+
52
+ </td>
53
+ </tr>
54
+ </table>
55
+
56
+ ---
57
+
58
+ ## 🚀 Quick Start
59
+
60
+ ### 📋 **Step 1: Setup Environment**
61
 
62
  ```bash
63
  cd simple_G_ai_bot
 
66
  Create a `.env` file in the project root:
67
 
68
  ```bash
69
+ # 🔐 .env
70
  OPENAI_API_KEY=your_openai_api_key_here
71
  ANTHROPIC_API_KEY=your_anthropic_api_key_here
72
  GOOGLE_API_KEY=your_google_api_key_here
73
  ```
74
 
75
+ ### 📦 **Step 2: Install Dependencies**
76
 
77
  ```bash
78
  uv sync
79
  ```
80
 
81
+ ### 🎯 **Step 3: Usage Examples**
82
+
83
+ <details>
84
+ <summary><b>🏗️ Dataset Curation</b></summary>
85
 
 
86
  Generate 50 urban outdoor samples:
87
  ```bash
88
  python main.py --mode data --samples 50 --urban --no-indoor
89
  ```
90
 
91
+ </details>
92
+
93
+ <details>
94
+ <summary><b>⚡ Single Image Analysis</b></summary>
95
+
96
  Benchmark GPT-4o on 5 samples:
97
  ```bash
98
  python main.py --mode benchmark --models gpt-4o --samples 5
99
  ```
100
 
101
+ </details>
102
+
103
+ <details>
104
+ <summary><b>🧠 Agentic Analysis</b></summary>
105
+
106
  Run multi-step analysis with Gemini:
107
  ```bash
108
  python main.py --mode agent --model gemini-2.5-pro --steps 10 --samples 5
109
  ```
110
 
111
+ </details>
112
+
113
+ ---
114
+
115
+ ## ⚙️ Configuration
116
+
117
+ ### 🔑 **Environment Variables**
118
+
119
+ | Variable | Description | Status |
120
+ |:---------|:------------|:------:|
121
+ | `OPENAI_API_KEY` | OpenAI API key for GPT models | 🔶 Optional |
122
+ | `ANTHROPIC_API_KEY` | Anthropic API key for Claude models | 🔶 Optional |
123
+ | `GOOGLE_API_KEY` | Google AI API key for Gemini models | 🔶 Optional |
124
+
125
+ ### 🛠️ **Command Line Options**
126
+
127
+ #### 🌟 **Common Options**
128
+ - `--mode` → Operation mode (`data`, `benchmark`, `agent`)
129
+ - `--samples` → Number of samples to process *(default: 10)*
130
+
131
+ #### 🏙️ **Data Mode Options**
132
+ - `--urban` → Focus on urban environments
133
+ - `--no-indoor` → Exclude indoor scenes
134
+
135
+ #### 📊 **Benchmark Mode Options**
136
+ - `--models` → AI model to use *(e.g., `gpt-4o`, `claude-3`, `gemini-pro`)*
137
+
138
+ #### 🤖 **Agent Mode Options**
139
+ - `--model` → AI model for agentic analysis
140
+ - `--steps` → Number of reasoning steps *(default: 5)*
141
+
142
+ ---
143
+
144
+ ## 🎯 Supported Models
145
+
146
+ <div align="center">
147
+
148
+ | Provider | Models | Status |
149
+ |:--------:|:-------|:------:|
150
+ | **🔵 OpenAI** | GPT-4o, GPT-4, GPT-3.5-turbo | ✅ Active |
151
+ | **🟣 Anthropic** | Claude-3-opus, Claude-3-sonnet, Claude-3-haiku | ✅ Active |
152
+ | **🔴 Google** | Gemini-2.5-pro, Gemini-pro, Gemini-pro-vision | ✅ Active |
153
 
154
+ </div>
155
 
156
+ ---
 
 
 
 
157
 
158
+ ## 📋 Requirements
159
 
160
+ > **Prerequisites:**
161
+ > - 🐍 Python 3.8+
162
+ > - 📦 UV package manager
163
+ > - 🔑 Valid API keys for desired AI providers
164
 
165
+ ---
 
 
166
 
167
+ ## 🔧 Installation
 
168
 
169
+ <table>
170
+ <tr>
171
+ <td>
172
 
173
+ **1️⃣** Clone the repository
174
+ ```bash
175
+ git clone <repository-url>
176
+ ```
177
 
178
+ **2️⃣** Navigate to project directory
179
+ ```bash
180
+ cd simple_G_ai_bot
181
+ ```
182
+
183
+ </td>
184
+ <td>
185
+
186
+ **3️⃣** Create `.env` file with your API keys
187
+ ```bash
188
+ touch .env
189
+ # Add your API keys
190
+ ```
191
 
192
+ **4️⃣** Install dependencies
193
+ ```bash
194
+ uv sync
195
+ ```
196
 
197
+ </td>
198
+ </tr>
199
+ </table>
200
 
201
+ **5️⃣** Run the bot with desired mode and options! 🎉
202
 
203
+ ---
 
 
 
 
204
 
205
+ ## 💡 Examples
206
 
207
+ ### 🏗️ **Basic Dataset Generation**
208
  ```bash
209
  python main.py --mode data --samples 20
210
  ```
211
 
212
+ ### 🌆 **Urban Scene Analysis**
213
  ```bash
214
  python main.py --mode data --samples 30 --urban --no-indoor
215
  ```
216
 
217
+ ### ⚔️ **Model Comparison**
218
  ```bash
219
+ # GPT-4o Analysis
220
  python main.py --mode benchmark --models gpt-4o --samples 10
221
+
222
+ # Claude-3 Analysis
223
  python main.py --mode benchmark --models claude-3-opus --samples 10
224
  ```
225
 
226
+ ### 🧠 **Advanced Agentic Workflow**
227
  ```bash
228
  python main.py --mode agent --model gemini-2.5-pro --steps 15 --samples 3
229
  ```
230
 
231
+ ---
232
+
233
+ ## 🔐 Security Note
234
+
235
+ > ⚠️ **Important**: Never commit your `.env` file to version control. Add `.env` to your `.gitignore` file to keep your API keys secure.
236
+
237
+ ---
238
+
239
+ <div align="center">
240
+
241
+ ## 📜 License
242
+
243
+ **MIT License** - see [LICENSE](LICENSE) file for details.
244
+
245
+ ---
246
 
247
+ <img src="https://img.shields.io/badge/Made%20with-❤️-red.svg" alt="Made with love">
248
+ <img src="https://img.shields.io/badge/AI%20Powered-🤖-blue.svg" alt="AI Powered">
249
+ <img src="https://img.shields.io/badge/Open%20Source-💚-green.svg" alt="Open Source">
250
 
251
+ **⭐ Star this repo if you find it useful!**
252
 
253
+ </div>